icp to article generation

• Outcome: Pass
• Latest audit: Sep 12, 2026 · 2:21 AM UTC
• Version: 1.0.0

Overview

This is a Markdown-only workflow for generating English marketing articles from user-provided business inputs, with no hidden execution, persistence, credential use, or exfiltration behavior found.

Install this if you specifically want a Chinese-guided workflow for producing English marketing articles. Avoid it for general writing, translation-only tasks, or non-English content unless you are comfortable overriding its English-output assumptions.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• YARA Signatures: Malware Match, Webshell Match, Cryptominer Match
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (10)

Natural-Language Policy Violations

High

• Confidence: 96% confidence
• Finding: Mandating English-only titles and article content without user opt-in can override user language preference and system-level localization or accessibility expectations. This is especially risky because the skill is written in Chinese but forces output in English, which may cause the agent to disregard user intent, produce unusable results, or mishandle multilingual contexts.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The skill description is broad enough to match many generic content-generation requests, which increases the chance of unintended activation. Over-broad routing can cause the agent to apply this workflow in contexts where the user did not ask for batch marketing article generation, leading to irrelevant data collection or inappropriate output behavior.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The activation condition relies on general user needs like 'quickly generate series content' without a precise scope, making skill selection ambiguous. In agent systems, ambiguous activation can misroute conversations into this workflow and steer users into unnecessary multi-step data collection and constrained outputs.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The template explicitly sets '内容语言' to '[English]' and earlier states that all product keywords must be in English for title generation. This is a language-policy constraint presented as a default requirement, with no opt-in choice or region-specific justification, which can violate organizational locale-choice policies.

Natural-Language Policy Violations

Medium

• Confidence: 86% confidence
• Finding: The file title and all instructional content are written exclusively in Chinese, which indicates a fixed language choice. Under the policy rule, forcing a specific language without user opt-in or a documented region-specific justification is a natural-language policy concern.

Natural-Language Policy Violations

Medium

• Confidence: 92% confidence
• Finding: The entire skill reference is written exclusively in Chinese and does not indicate that language selection is optional or that the skill is intended only for a Chinese-speaking or region-specific context. Under the policy rule, forcing a specific language without opt-in is a natural-language locale violation.

Natural-Language Policy Violations

Medium

• Confidence: 92% confidence
• Finding: This markdown file presents all guidance exclusively in Chinese, and nowhere indicates that the user can choose another language or that the Chinese-only format is a documented regional requirement. Under the policy rule for language or locale constraints, forcing a single language without user opt-in is a natural-language policy concern.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The document states that every recommended title must be written in English, which imposes a language requirement as a hard rule. Under the policy, forcing a specific language without user opt-in or clear justification is a natural-language policy violation.

YARA rule 'network_reconnaissance': Network reconnaissance and scanning patterns [hacktools]

Medium

• Category: YARA Match

Content

How Startups Build Growth Systems" (Keyword: **growth**)
- "4 Key Points for SMEs to Break Through Growth Bottlenecks" (Keyword: **SME**)
- "Scaling Operations Guide: From 10-Person to 100-Person Teams" (Keyword: **operations**)

### Competitive Advantage Category
- "3 Collaboration Tools Your Competitors Are Already Using" (Keyword: **collaboration**)
- "How to Build Differentiated Advantages in Fierce Competition?" (Keyword: **competition**)
- "Digital Transformation: The Opportunity Window for Overtaking" (Keyword: **digital**)

## Matching with Article Types

| Article Type | Recommended Title Template | Example |
|-------------|---------------------------|---------|
| **Pain Point Analysis** | Template 4: Pain Point Revelation + Consequence Warning | "The Cost of Ignoring Team Collaboration: You May Be Losing Core Talent" |
| **Methodology** | Template 1: Problem + Number + Solution | "Low Team Collaboration Efficiency? 5 Methods to Improve It Fast" |
| **Case Study** | Template 3

• Confidence: 65% confidence
• Finding: YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Natural-Language Policy Violations

Low

• Confidence: 88% confidence
• Finding: This markdown file presents all instructions and examples exclusively in Chinese, and there is no natural-language indication that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the language/locale policy rule, forcing a single language without opt-in can be a policy concern.

Static analysis

No suspicious patterns detected.